Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Low-Resource Speech Recognition and Keyword-Spotting Read chapter Read first chapter

2017 | OriginalPaper | Chapter

Improving of LVCSR for Causal Czech Using Publicly Available Language Resources

Authors : Petr Mizera, Petr Pollak

Published in: Speech and Computer

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The paper presents the design of Czech casual speech recognition which is a part of the wider research focused on understanding very informal speaking styles. The study was carried out using the NCCCz corpus and the contributions of optimized acoustic and language models as well as pronunciation lexicon optimization were analyzed. Special attention was paid to the impact of publicly available corpora suitable for language model (LM) creation. Our final DNN-HMM system achieved in the task of casual speech recognition WER of 30–60% depending on LM used. The results of recognition for other speaking styles are presented as well for the comparison purposes. The system was built using KALDI toolkit and created recipes are available for the research community.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Improved Speaker Adaptation by Combining I-vector and fMLLR with Deep Bottleneck Networks
next chapter Improving Performance of Speaker Identification Systems Using Score Level Fusion of Two Modes of Operation
Literature
1.
Cui, J., Ramabhadran, B., Cui, X., Rosenberg, A., Kingsbury, B., Sethy, A.: Recent improvements in neural network acoustic modeling for LVCSR in low resource languages. In: Proceedings of Interspeech 2014: 15th Annual Conference of the International Speech Communication Association, Singapore (2014)
2.
Seltzer, L.M., Dong, Y., Yongqiang, W.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, Vancouver, Canada (2013)
3.
Korvas, M., Plátek, O., Dušek, O., Žilka, L., Jurčíček, F.: Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license. In: Proceedings of LREC 2014: 9th International Conference on Language Resources and Evaluation, Reykjavik, Iceland, pp. 365–370 (2014)
4.
Barras, C., Lamel, L., Gauvain, J.L.: Automatic transcription of compressed broadcast audio. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, USA, pp. 265–268 (2001)
5.
Nouza, J., Ždánský, J., Červa, P.: System for automatic collection, annotation and indexing of Czech broadcast speech with full-text search. In: Proceedings of 15th IEEE MELECON Conference, La Valleta, Malta, pp. 202–205 (2010)
6.
Nouza, J., Blavka, K., Bohac, M., Cerva, P., Málek, J.: System for producing subtitles to internet audio-visual documents. In: 38th International Conference on Telecommunications and Signal Processing, TSP 2015, Prague, Czech Republic, pp. 1–5, 9–11 July 2015
7.
Psutka, J., Psutka, J., Ircing, P., Hoidekr, J.: Recognition of spontaneously pronounced TV ice-hockey commentary. In: Proceedings of ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition, Tokyo, pp. 83–86 (2003)
8.
Lehr, M., Gorman, K., Shafran, I.: Discriminative pronunciation modeling for dialectal speech recognition. In: Proceedings of Interspeech 2014, Singapore, pp. 1458–1462 (2014)
9.
Nouza, J., Silovský, J.: Adpating lexical and language models for transcription of highly spontaneous spoken Czech. In: Proceedings of Text, Speech, and Dialogue, LNAI, vol. 6231, Brno, Czech Republic, pp. 377–384 (2010)
10.
Byrne, W., et al.: Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans. Speech Audio Process. 12(4), 420–435 (2004)CrossRef
11.
Ernestus, M., Kočková-Amortová, L., Pollák, P.: The Nijmegen corpus of casual Czech. In: Proceedings of LREC 2014: 9th International Conference on Language Resources and Evaluation, Reykjavik, Iceland, pp. 365–370 (2014)
12.
Torreira, F., Adda-Decker, M., Ernestus, M.: The Nijmegen corpus of casual French. Speech Commun. 52, 201–221 (2010)CrossRef
13.
Prochazka, V., Pollak, P.: Conversational speech from Nijmegen corpus of casual Czech by general ASR language models. In: Production and Comprehension of Conversational Speech, pp. 34–35 (2011)
14.
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82–97 (2012)CrossRef
15.
Vesely, K., Karafiat, M., Grezl, F.: Convolutive bottleneck network features for lVCSR. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), December 2011
16.
Pollak, P., Cernocky, J.: Czech SPEECON adult database. Technical report (2004)
17.
18.
Prochazka, V., Pollak, P., Zdansky, J., Nouza, J.: Performance of Czech speech recognition with language models created from public resources. Radioengineering 20, 1002–1008 (2011)
19.
20.
Schuppler, B., Adda-Decker, M., Morales-Cordovilla, J.A.: Pronunciation variation in read and conversational Austrian German. In: Proceedings of Interspeech 2014, Singapore (2014)
21.
Kolman, A., Pollak, P.: Speech reduction in Czech. In: Proceedings of LabPhone 14, The 14th Conference on Laboratory Phonology, Tokyo, Japan (2014)
22.
Rajnoha, J., Pollák, P.: Czech spontaneous speech collection and annotation: the database of technical lectures. In: Esposito, A., Vích, R. (eds.) Cross-Modal Analysis of Speech, Gestures, Gaze and Facial Expressions. LNCS, vol. 5641, pp. 377–385. Springer, Heidelberg (2009). doi:10.​1007/​978-3-642-03320-9_​35 CrossRef
23.
Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of ASRU 2011, IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (2011)
24.
Fousek, P., Pollak, P.: Efficient and reliable measurement and simulation of noisy speech background. In: Proceedings of EUROSPEECH 2003, 8-th European Conference on Speech Communication and Technology, Geneve, Switzerland (2003)
25.
Borsky, M., Mizera, P., Pollak, P.: Noise and channel normalized cepstral features for far-speech recognition. In: Proceedings of SPECOM 2013, The 15th International Conference on Speech and Computer, Pilsen, Czech Republic (2013)
Metadata
Title
Improving of LVCSR for Causal Czech Using Publicly Available Language Resources
Authors
Petr Mizera
Petr Pollak
Copyright Year
2017
Book
Speech and Computer

Print ISBN: 978-3-319-66428-6

Electronic ISBN: 978-3-319-66429-3

Copyright Year: 2017

DOI
https://doi.org/10.1007/978-3-319-66429-3_42

Premium Partner

    Image Credits